☆ 4.6 Article

MAMIQA: No-Reference Image Quality Assessment Based on Multiscale Attention Mechanism With Natural Scene Statistics

IEEE SIGNAL PROCESSING LETTERS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Electrical & Electronic

SPIQ: A Self-Supervised Pre-Trained Model for Image Quality Assessment

Pengfei Chen et al.

Summary: Blind image quality assessment (BIQA) has made significant progress with the rapid advances in deep learning techniques. Prior methods typically rely on pre-trained models from ImageNet to address the data shortage problem, but these models may not be optimal for BIQA tasks that are considerably different from image classification. In this paper, we propose a self-supervised pre-training approach using abundant unlabeled data to tackle this issue. By generating distorted images from high-quality samples, our method is able to predict feature representations to capture quality-aware information for BIQA task. Experimental results show that the learned pre-trained model significantly benefits existing learning based IQA models.

IEEE SIGNAL PROCESSING LETTERS (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

MTT: Multi-Scale Temporal Transformer for Skeleton-Based Action Recognition

Jun Kong et al.

Summary: The proposed method introduces a multi-scale temporal transformer (MTT) for skeleton-based action recognition, embedding raw skeleton data using graph convolutional network (GCN) blocks and multi-scale temporal embedding modules (MT-EMs) to extract features in various temporal scales. Transformer encoders (TE) are introduced to integrate embeddings and model long-term temporal patterns, while a task-oriented lateral connection (LaC) is proposed to align semantical levels and predict action categories efficiently. The method achieves state-of-the-art results on three large datasets, NTU-RGBD 60, NTU-RGBD 120, and Kinetics-Skeleton 400.

IEEE SIGNAL PROCESSING LETTERS (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Light Field Image Super-Resolution With Transformers

Zhengyu Liang et al.

Summary: This paper proposes a Transformer-based method for LF image super-resolution, which effectively utilizes the beneficial information in LF to improve the SR performance.

IEEE SIGNAL PROCESSING LETTERS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

VCRNet: Visual Compensation Restoration Network for No-Reference Image Quality Assessment

Zhaoqing Pan et al.

Summary: This study proposed a no-reference image quality assessment method based on the visual compensation restoration network, which efficiently handles image restoration tasks with non-adversarial models, thereby improving the accuracy of image quality prediction.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2022)

添加到收藏夹

Proceedings Paper Computer Science, Software Engineering

GreenBIQA: A Lightweight Blind Image Quality Assessment Method

Zhanxuan Mei et al.

Summary: In this work, a lightweight image quality assessment model called GreenBIQA is proposed. It adopts an unsupervised feature generation method and a supervised feature selection method to extract quality-aware features, and then predicts quality scores using an XGBoost regressor. Experimental results show that GreenBIQA is competitive in performance against state-of-the-art DNNs with lower complexity and smaller model sizes.

2022 IEEE 24TH INTERNATIONAL WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING (MMSP) (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

SMART: Semantic-Aware Masked Attention Relational Transformer for Multi-label Image Recognition

Hongjun Wu et al.

Summary: This paper proposes a SMART method for multi-label image recognition, which improves the performance of image recognition by learning label co-occurrence and filtering redundant dependencies. The method achieves state-of-the-art results on multiple datasets.

IEEE SIGNAL PROCESSING LETTERS (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

CSformer: Cross-Scale Features Fusion Based Transformer for Image Denoising

Haitao Yin et al.

Summary: This paper proposes a novel Transformer-based image denoising method, CSformer, which leverages cross-scale feature fusion and a mixed global-local Transformer module to improve the denoising performance. Experimental results show the superiority of CSformer over state-of-the-art methods on various datasets and noise levels.

IEEE SIGNAL PROCESSING LETTERS (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency

S. Alireza Golestaneh et al.

Summary: This paper proposes a novel model that combines CNN and Transformer to address the No-Reference Image Quality Assessment (NR-IQA) task. It captures both local and non-local features from the input image. The model leverages self-consistency as a source of self-supervision to improve the robustness of NR-IQA models. Experimental results demonstrate that the model achieves state-of-the-art results on various datasets.

2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022) (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

Hybrid Transformer-CNN for Real Image Denoising

Mo Zhao et al.

Summary: In this study, a hybrid denoising model called TECDNet is proposed, combining the advantages of Transformer and CNN. The Transformer is used in the encoder to improve representation capability, while a residual CNN is adopted in the decoder to reduce computational complexity. Experimental results demonstrate that TECDNet achieves state-of-the-art denoising performance with relatively low computational cost.

IEEE SIGNAL PROCESSING LETTERS (2022)

添加到收藏夹

Article Engineering, Electrical & Electronic

HashFormer: Vision Transformer Based Deep Hashing for Image Retrieval

Tao Li et al.

Summary: Deep image hashing maps input images to compact binary codes using deep neural networks for efficient retrieval. This study proposes a pure transformer-based framework called HashFormer to tackle the deep hashing task, achieving promising results compared to existing methods. The method utilizes vision transformers as the backbone and introduces an average precision loss to optimize retrieval accuracy.

IEEE SIGNAL PROCESSING LETTERS (2022)

添加到收藏夹

Article Computer Science, Theory & Methods

Screen Content Quality Assessment: Overview, Benchmark, and Beyond

Xiongkuo Min et al.

Summary: This article provides a systematic and timely review on the research field of screen content quality assessment, covering background, characteristics, methodologies and measures, state-of-the-art evaluation, generalizations to QoE assessment, and unresolved challenges and future research directions.

ACM COMPUTING SURVEYS (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

TRANSFORMER FOR IMAGE QUALITY ASSESSMENT

Junyong You et al.

Summary: This paper investigates the application of Transformer in Image Quality (TRIQ) assessment, proposing a new architecture that achieves outstanding performance on publicly available image quality databases.

2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Saliency-Guided Transformer Network combined with Local Embedding for No-Reference Image Quality Assessment

Mengmeng Zhu et al.

Summary: This paper proposes a novel Saliency-Guided Transformer Network combined with Local Embedding (TranSLA) for No-Reference Image Quality Assessment, which integrates saliency prediction with Transformer to guide the model to focus on the Region-of-interest (RoI). Experimental results show that this method significantly outperforms the state-of-the-art on two large-scale NR-IQA benchmarks.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2021) (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network

Weixia Zhang et al.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2020)

添加到收藏夹

Review Computer Science, Information Systems

Perceptual image quality assessment: a survey

Zhai Guangtao et al.

SCIENCE CHINA-INFORMATION SCIENCES (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

KonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment

Vlad Hosu et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression

Jun Qi et al.

IEEE SIGNAL PROCESSING LETTERS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep CNN-Based Blind Image Quality Predictor

Jongyoo Kim et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Generating Image Distortion Maps Using Convolutional Autoencoders With Application to No Reference Image Quality Assessment

Sathya Veera Reddy Dendi et al.

IEEE SIGNAL PROCESSING LETTERS (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Authentically Distorted Image Quality Assessment by Learning From Empirical Score Distributions

Qiuping Jiang et al.

IEEE SIGNAL PROCESSING LETTERS (2019)

添加到收藏夹

Article Engineering, Electrical & Electronic

Blind Image Quality Estimation via Distortion Aggravation

Xiongkuo Min et al.

IEEE TRANSACTIONS ON BROADCASTING (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment

Sebastian Bosse et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

End-to-End Blind Image Quality Assessment Using Deep Neural Networks

Kede Ma et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2018)

添加到收藏夹

Article Computer Science, Information Systems

Blind Quality Assessment Based on Pseudo-Reference Image

Xiongkuo Min et al.

IEEE TRANSACTIONS ON MULTIMEDIA (2018)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning

Kwan-Yee Lin et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

PieAPP: Perceptual Image-Error Assessment through Pairwise Preference

Ekta Prashnani et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Massive Online Crowdsourced Study of Subjective and Objective Picture Quality

Deepti Ghadiyaram et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2016)

添加到收藏夹

Article Engineering, Electrical & Electronic

Making a Completely Blind Image Quality Analyzer

Anish Mittal et al.

IEEE SIGNAL PROCESSING LETTERS (2013)

添加到收藏夹

Article Computer Science, Artificial Intelligence

No-Reference Image Quality Assessment in the Spatial Domain

Anish Mittal et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2012)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain

Michele A. Saad et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2012)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality

Anush Krishna Moorthy et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2011)

添加到收藏夹

Review Neurosciences

What attributes guide the deployment of visual attention and how do they do it?

JM Wolfe et al.

NATURE REVIEWS NEUROSCIENCE (2004)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.